从一个网页中获取所有的超链接

桃扇骨 2022-08-23 15:54 156阅读 0赞

**从一个网页中获取所有的超链接**

<table> 
 <tbody> 
 <tr> 
 <td> /** &nbsp;&nbsp; @version 1.01 2004-06-04 &nbsp;&nbsp; @author Cay Horstmann */ import java.io.*; import java.net.*; import java.util.regex.*; /** &nbsp;&nbsp; This program displays all URLs in a web page by &nbsp;&nbsp; matching a regular expression that describes the &nbsp;&nbsp; &lt;a href=...&gt; HTML tag. Start the program as &nbsp;&nbsp; java HrefMatch URL */</td> 
 </tr> 
 <tr> 
 <td colspan="2"> public class HrefMatch { &nbsp;&nbsp; public static void main(String[] args) &nbsp;&nbsp; { &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; try &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; { &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; // get URL string from command line or use default &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; String urlString; &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; if (args.length &gt; 0) urlString = args[0]; &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; else urlString = "http://java.sun.com"; &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; // open reader for URL &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; InputStreamReader in = new InputStreamReader(new URL(urlString).openStream()); &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; // read contents into string buffer &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; StringBuilder input = new StringBuilder(); &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; int ch; &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; while ((ch = in.read()) != -1) input.append((char) ch); &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; // search for all occurrences of pattern &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; String patternString = "&lt;a//s+href//s*=//s*(/"[^/"]*/"|[^//s&gt;])//s*&gt;"; &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Pattern pattern = Pattern.compile(patternString, Pattern.CASE_INSENSITIVE); &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Matcher matcher = pattern.matcher(input); &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; while (matcher.find()) &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; { &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; int start = matcher.start(); &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; int end = matcher.end(); &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; String match = input.substring(start, end); &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; System.out.println(match); &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; } &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; } &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; catch (IOException e) &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; { &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; e.printStackTrace(); &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; } &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; catch (PatternSyntaxException e) &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; { &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; e.printStackTrace(); &nbsp;&nbsp;&nbsp;&nbsp;&nbsp; } &nbsp;&nbsp; } } 运行： java HrefMatch http://www.128kj.com &lt;a href="linktype.jsp?type=1"&gt; &lt;a href="articleType_flex.html"&gt; &lt;a href="articleType_flex.html"&gt; &lt;a href="morephp.html"&gt; &lt;a href="morephp.html"&gt; &lt;a href="morejava.html"&gt; &lt;a href="morejava.html"&gt; &lt;a href="moreajax.html"&gt; &lt;a href="moreajax.html"&gt; &lt;a href="morejsp.html"&gt; &lt;a href="morejsp.html"&gt; &lt;a href="morejavascript.html"&gt; &lt;a href="morejavascript.html"&gt; &lt;a href="morexml.html"&gt; &lt;a href="morexml.html"&gt; &lt;a href="morecss.html"&gt; &lt;a href="morecss.html"&gt; &lt;a href="index7.html"&gt; &lt;a href="morePic.html"&gt; &lt;a href="moreFeibiao.html"&gt; &lt;a href="article/article45/logo/index0.html"&gt; &lt;a href="article/article46/bannerpic/index0.html"&gt; &lt;a href="moreTem.html"&gt; &lt;a href="moreTubiao.html"&gt; &lt;a href="moreJspSrc.html"&gt; &lt;a href="morePhpSrc.html"&gt; &lt;a href="article/article47/bg/index0.html"&gt; &lt;a href="morehtml.html"&gt; &lt;a href="morehtml.html"&gt; &lt;a href="morephotoshop.html"&gt; &lt;a href="morephotoshop.html"&gt; &lt;a href="http://www.miibeian.gov.cn"&gt;</td> 
 </tr> 
 </tbody> 
</table>